it's the 4bit quantized version. you won't be able to fit the biggest one on an iPhone yet due to RAM limits
HARDWARE
-
Best Offline Phone AI Models for Survival Situations
By
–
Which AI model should you carry as an offline backup?
— Aaron Ng (@localghost) 15 janvier 2025
I tested phone AI models on 500+ survival questions to find out. pic.twitter.com/n1V9bcNzrEWhich AI model should you carry as an offline backup? I tested phone AI models on 500+ survival questions to find out.
-
A100 DGX Hardware Issues Despite Plans for New Purchase
By
–
I am certainly going to get one of these, but my $200k A100 DGX has been an absolute lemon — replaced three times under warranty, and just last week the CPU cooling system appears to have died. Hopefully just needs new thermal paste.
-
AI Breakthroughs: Super Intelligence, Nvidia, Microsoft Investments
By
–
𝕀𝔸 : 𝕝𝕖 𝕘𝕣𝕒𝕟𝕕 𝕔𝕙𝕒𝕞𝕓𝕒𝕣𝕕𝕖𝕞𝕖𝕟𝕥 Super intelligence : la surenchère d’OpenAI Nvidia fait le show au #CES2025
Microsoft va investir 80 Mrds$ NeuroXess concurrence Neuralink Et bien plus encore sont au menu de la 22 e édition de 𝕄𝕖𝕤 𝔽𝕝𝕒𝕤𝕙𝕤 -
EXOPULSE Mollii Suit Uses AI Electrical Stimulation for Muscle Spasms
By
–
Now that's progress!
— Pascal Bornet (@pascal_bornet) 15 janvier 2025
EXOPULSE Mollii Suit neutralizes the spasms of its host by electrically stimulating the muscle opposite to the one that malfunctions. The result is absolutely breathtaking.
By choosing to harmonize with technology, we become more human, we become… pic.twitter.com/5eawFSEDHTNow that's progress! EXOPULSE Mollii Suit neutralizes the spasms of its host by electrically stimulating the muscle opposite to the one that malfunctions. The result is absolutely breathtaking. By choosing to harmonize with technology, we become more human, we become
-
Quantum Computing Transitions From Theory to Business Practice
By
–
2025 marks an essential time for businesses and developers to actively engage with quantum computing as it could transition from a theoretical concept to a practical tool. https://t.co/q37JlXeiUm
— Antonio Grasso (@antgrasso) 15 janvier 20252025 marks an essential time for businesses and developers to actively engage with quantum computing as it could transition from a theoretical concept to a practical tool.
-
Hardware Strategy: Productivity Suite as Trojan Horse
By
–
This is a smart way to build up to their eventual consumer hardware device. Getting stuff done is the key idea behind every OS. It might not look like it, but this is a trojan horse for:
— Aaron Ng (@localghost) 15 janvier 2025
– Calendaring
– Notes
– Todos
All in one go. https://t.co/SCaYq3qLNLThis is a smart way to build up to their eventual consumer hardware device. Getting stuff done is the key idea behind every OS. It might not look like it, but this is a trojan horse for: – Calendaring
– Notes
– Todos All in one go. -
Leveraging Unified Memory in PyTorch with Blackwell GH200
By
–
Totally missed that and that sounds awesome. Genuine question, how do you leverage unified memory in PyTorch though? Was discussing this with a user who was using Blackwell GH200 the other day here:
-
WSE-3 Wafer Scale Engine Achieves 93% Silicon Utilization
By
–
Despite being the world’s largest computer chip, the WSE-3 achieves 93% silicon utilization—higher than today’s leading GPU. A tiny core, a self-healing fabric, and a clean software abstraction – that’s how you do wafer scale.
-
WSE Defect Tolerance: 164x Better Silicon Efficiency
By
–
One way to measure defect tolerance is to look at the amount of die area. Assuming 0.001 defects per mm^2, GPUs will see 59 defects disabling 361mm^2 of silicon. On the WSE, it sees 46 defects and loses just 2.2mm^2. That's a 164x reduction in dead silicon area!